Unevenly Spaced Time Series from Network Traffic
Josef Koumar, Tomáš Čejka · 2023
Reliable detection of security events is essential for network security. Therefore, a suitable traffic representation and model are required. Contrary to the currently used approaches, this paper presents Unevenly Spaced Time Series (USTS) as a feasible representation of network traffic with several brilliant benefits for analysis. The article concerns several types of USTS. A dataset captured on a real ISP network was created to evaluate the properties of USTS. The dataset contains over 35 million time series. We experimentaly proved the USTS is suitable for network traffic analysis and allow automatic processing, e.g., to classify network traffic.